Has anyone had any experience of evaluating the discrimination of a
competing risks survival model using an approach analogous to the area under
the ROC curve sometimes used for logistic regression? I would appreciate any
advice.
Claire
Claire Williams
Statistician
Wellcome Trust Clinical Research Facility
Western General Hospital
Crewe Road South
Edinburgh
EH4 2XU
0131 537 3352
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.
|